Back

Speaker "Nikunja Dash" Details Back

 

Topic

How to efficiently manage groundwater resources using GA-based ANN algorithm?

Abstract

The accurate prediction of groundwater level is important for the efficient use and management of groundwater resources, particularly in sub-humid regions where water surplus in monsoon season and water scarcity in non-monsoon season is a common phenomenon. In this paper, an attempt has been made to develop a hybrid neural model (ANN-GA) employing an artificial neural network (ANN) model in conjunction with famous optimization strategy called genetic algorithms (GA) for accurate prediction of groundwater levels in the lower Mahanadi river basin of Orissa State, India. Three types of functionally different algorithm-based ANN models (viz. back-propagation (GDX), Levenberg–Marquardt (LM) and Bayesian regularization (BR)) were used to compare the strength of proposed hybrid model in the efficient prediction of groundwater fluctuations. The ANN-GA hybrid modeling was carried out with lead-time of 1 week and study mainly aimed at November and January months of a year. Overall, simulation results suggest that the Bayesian regularization model is the most efficient of the ANN models tested for the study period. However, a strong correlation between the observed and predicted groundwater levels was observed for all the models. The results reveal that the hybrid GA-based ANN algorithm is able to produce better accuracy and performance in medium and high groundwater level predictions compared to conventional ANN techniques including Bayesian regularization model. Furthermore, the study shows that hybrid neural models can offer significant implications for improving groundwater management and water supply planning in semi-arid areas where aquifer information is not available.
Who is this presentation for?
Any one is interested to learn about Applied Artificial Intelligence through scientific modelling to solve day-today problem.
Prerequisite knowledge:
Not required
What you'll learn?
Will Share the Knowledge

Profile

Nikunja Dash has 6 years of research and development experience in Artificial Intelligence (Artificial Neural Network), Genetic Algorithm and MATLAB. He is one of the prominent researchers in application of Artificial intelligence using ANN and GA hybrid technology. He is also a globally recognized author and scientist in field of Ground Water.  He has co-authored a research paper named ‘Hybrid Neural Modeling for Groundwater Level Prediction’ and alsoco-authored an innovative technology book named ‘Concepts and Applications in Agricultural Engineering’. Hisareas of expertizes include Mainframe technologiesand also ANN/GA based Artificial intelligence technologies. He is further interested to work on expansion of Artificial intelligence using data power of Mainframe and solve problems of modern world (and open to any industrial or individual collaboration on same).